MCP debug server for AI coding agents. Debug Python, Node.js, Java & browser JavaScript with breakpoints, stepping, variable inspection, and real-time event capture. Works with Claude Code, Cursor, Windsurf, or any MCP client — no IDE required.

MCP Server for browser debugging via CDP

NIA AI Web Evaluation Agent MCP Server - Autonomous browser testing and debugging

MCP server that controls a running Chrome over the Chrome DevTools Protocol (CDP). It connects to Chrome's remote-debugging endpoint and exposes browser control as MCP tools.

Safari DevTools MCP — real browser debugging with network interception, DOM inspection, and CSS analysis for AI agents on macOS

Safari DevTools MCP — real browser debugging with network interception, DOM inspection, cookie/storage management, and CSS analysis for AI agents on macOS

Lets Claude Code debug a page already open in your real Firefox session — read live console/network activity, eval JS, snapshot the DOM, and take screenshots via an MCP server, without spinning up a separate automated browser.

FlowLens is an open-source MCP server that gives your coding agent (Claude Code, Cursor, Copilot, Codex) full browser context for in-depth debugging and regression testing.

OpenCode Browser MCP — Chrome automation plugin for OpenCode via WebSocket + Chrome Extension. 50+ tools: tabs, CDP debugging, network intercept, visual click, session, accessibility and more.

Lean, LLM-first browser automation MCP server. Gives Claude, OpenCode, or any MCP client a real browser to navigate, interact with, and debug web apps.

🛠️ Control and inspect a live Chrome browser with `chrome-devtools-mcp` for reliable automation, debugging, and performance insights.

This web browser has been designed to help your agent debug and develop complex web applications. (MCP Server)

Pagewright: give your AI agent a real browser. MCP server + Chrome extension for page snapshots, screenshots, real clicks, layout audits, CSS debugging and web scraping, in the browser you already use.

MCP server that bridges Claude Desktop (or any other local app supporting MCP) with Selenix for browser automation and testing. Enables creating, running, debugging, and managing browser automation tests through natural language.

MCP server that bridges Claude Desktop (or any other local app supporting MCP) with Selenix for browser automation and testing. Enables creating, running, debugging, and managing browser automation tests through natural language.

Your agent works. Your cursor stays yours. Background-first MCP + CLI for Chrome, Edge and native apps. No browser remote debugging.

Control your real browser and ScriptCat from the CLI, AI clients (MCP) and scripts: tabs, browser data, page automation, debugging, raw CDP, and userscript management — one cross-platform binary.

Turn your everyday Chrome into a universal MCP server - one extension + one endpoint for every MCP client (38 browser tools: snapshot/click/fill, network, console, cookies, PDF, CDP debug)

MCP server that lets Claude Code, Codex & AI agents drive a real Chrome browser with JEV (TypeSafe System One): ~100 ms typed decisions, calibrated confidence, human-in-the-loop questions, safety gates and a debug trace.

MCP server that drives the Chrome/Edge tabs you already have open and signed in — local extension pairing, no remote debugging port, no separate automation browser. Tools for AX snapshots, native click/type/fill/hover/drag/scroll, batch steps, waits, navigation, dialogs, upload, screenshots, JS evaluate and console/network logs.

This web browser has been designed to help your agent debug and develop complex web applications.

AI-powered MCP server for JavaScript reverse engineering, security auditing, browser automation and dynamic analysis. Features CDP debugging, JS deobfuscation, network interception, memory scanning, Frida instrumentation, V8 inspector, WASM analysis, and cross-domain evidence correlation.

Browser-based real-time modding tool for jailbroken PS5 consoles: find values, make cheats, debug, and learn how it is done.

MCP server, CLI, and web dashboard for Ren'Py visual-novel development — inspect, drive and debug a running game from an AI agent or the browser

Develop and debug FoloToy AI Passport firmware without the device: an ESP32-C3 emulator that runs unmodified ESP-IDF images in the browser (WebAssembly) or on macOS and Windows, with a CLI and an MCP server for AI agents.

🚀 Local-first C# Platform, ✍️ Write, compile and run C# in the browser with .NET 10 WebAssembly + Roslyn, 🔌 expose it to AI agents via an MCP server, and 🤖 add an optional local AI assistant (Ollama) with RAG to review, debug, explain and test your code. 🔒 No account, No Install, No Server, No Cloud ~ Run Everything Locally.

SAP ABAP MCP is a local-first Model Context Protocol server that enables AI coding agents to develop, test, analyze, and operate SAP ABAP systems through the official ABAP Development Tools HTTP services. It supports repository search and source editing, structured DDIC workflows, enhancement inspection, paged package navigation, source-backed object creation, semantic services, activation, ABAP Unit and ATC, transports, abapGit, RAP generation, debugging, bounded class and executable-program profiling, runtime dumps, traces and feeds, cross-system comparison, dependency analysis, guarded refactoring, and an opt-in same-origin Screen/GUI Status bridge. Curated compact, development, and assurance presets reduce tool-schema token use without removing capabilities from the default surface. The default local stdio mode can be extended with governed self-hosted Streamable HTTP, API-key roles, OIDC/JWT authentication, request-scoped SAP bearer forwarding, per-session isolation, rate limits, structured audit logs, or a side-effect-free embeddable Node.js API. It also includes browser OAuth Authorization Code with PKCE, a read-only transport assurance CLI and GitHub Action, BTP service-key profile import, and live-SAP evidence tooling. SAP profiles and credentials remain on the user's computer, with passwords and OAuth credentials protected by macOS Keychain or Windows DPAPI. SAP-dependent capabilities are validated against the user's own SAP release, configuration, and authorizations.

Visual UI testing and debugging MCP server with Playwright, screenshots, DOM inspection, workflow validation, and visual diffs.

Give your AI agent Chrome DevTools. Debug Chromium apps through console, network, DOM, accessibility, screenshots, and change analysis.

Rogue Chrome DevTools MCP - inspect and debug pages from agents

Standalone connector for BrowserTools MCP. Only needed when several MCP clients must share one browser session — browser-tools-mcp now embeds this automatically.

Kaboom Agentic Browser is an AI debugger, inspector, and verification toolkit for local-first browser development workflows.

MCP server for Playwright browser automation and CSSOM inspection

MCP server for browser inspection with Puppeteer - network monitoring and console error tracking

MCP server that exposes browser console, error, and network events streamed from the MCP Browser Console Chrome Extension.

Gasoline Agentic Browser is an AI Debugger, Inspector, and Observability toolkit. It acts as Chrome DevTools for AI Agents using the Model Context Protocol (MCP).

Chrome DevTools for coding agents

MCP Server and CLI for IronBee DevTools

Chrome DevTools Protocol integration for Model Context Protocol

Claude Code marketplace plugins: agnt (browser superpowers), lci (code intelligence), tools (combined)

Eyes & Hands for AI in the Browser — Chrome extension + MCP server giving AI agents full browser visibility and control

Container packaging for the chrome-devtools-mcp.

StandardBeagle Super Toolkit 2026 - AI Agent & Code Intelligence Bundle

Deterministic rendered-page → LLM context MCP server: which rule, which file, which line — and why it wins.

MCP Server for Development Tooling - Project Detection, Process Management, and Reverse Proxy with Frontend Instrumentation

AI Agent-first JS 逆向 MCP Server：有头 Chrome 调试、断点、网络/WebSocket 分析、Patchright 反检测，可选 CloakBrowser。

A Model Context Protocol (MCP) server that provides web development tools for AI assistants. Enables browser automation, DOM inspection, network monitoring, and console analysis through Playwright.

An MCP Server for Chrome DevTools, following the Chrome DevTools Protocol. Integrates with Claude Desktop and Claude Code.

Local browser control and temporal visual evidence for AI agents — an MCP server that drives Chrome, continuously records it, and answers what-happened questions from retained frames, storyboards, filmstrips, and browser events

Chrome extension + MCP server — record, replay, and understand what's behind the pixels. Timestamped visual-API correlation for Claude Code and any MCP client.

Attach-only MCP server in Go that lets Codex CLI or Claude Code inspect a running Chrome over CDP and record JSONL timelines. Early release (v0.0.1).

MCP server for AI coding agents - process management, reverse proxy with traffic logging, browser instrumentation, and sketch mode

MCP server: your coding agent clicks a button and sees which browser and Node lines ran.

Zero-config dev server & browser runtime error sensor for AI coding agents (Claude Code, Codex, Cursor, Antigravity) via MCP.

Your AI coding agent can finally see what your dev server sees. Real-time runtime, bundler (Vite/Next.js/Storybook), TypeScript, and browser errors for Claude Code, Codex, Cursor, Antigravity, and Copilot via MCP.

DevTools for any WebView — no remote-debugging port required. Works in Safari/iOS WebView/Lark Web App and more.

AI agent that walks your site’s key journeys (purchase, sign-up, lead) in a real browser and checks that GA4, Google Ads, Meta and TikTok tags fire correctly. Works from the CLI or as an MCP server in your AI app.

MCP server that lets AI assistants automate, debug and screenshot any Electron app over the Chrome DevTools Protocol — no app changes required.

Enable runtime analysis and control of AI agents with a dynamic process hacking server similar to Process Hacker for enhanced debugging and integration.

Playwright end-to-end testing MCP server — run, debug and inspect E2E tests from any AI agent: failure analysis, live DOM inspection, selector validation, visual diffs, flaky-test diagnosis.